INDEX

Explanations

statements indicating potential conditions, uncertain situations, or possibilities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BagConstraints

-0.30

neider

-0.28

sem

-0.26

Throwable

-0.26

 Maxim

-0.24

 rég

-0.24

ORA

-0.24

et

-0.24

bin

-0.24

ften

-0.23

POSITIVE LOGITS

Autoritní

0.75

 autorytatywna

0.73

seamnă

0.70

 resulted

0.69

 coincided

0.66

 Happened

0.66

 occurred

0.66

ConstraintMaker

0.64

 HAPPENED

0.64

 occur

0.64

Activations Density 0.762%

statements indicating potential conditions, uncertain situations, or possibilities

No Comments

No Known Activations